A modern sensor based health care society where prevention is actualized through a multi factor correlation of real-time data augmented by behavioral rewards and the Internet of Things is going to snatch economic victory from the jaws of defeat. In today’s world we theorize about the higher incidence of obesity due to fructose intake, environmental factors causing metabolic slowdown, and possibly many other factors. It is the same for asthma, autism, autoimmune disease, and diabetes. We are drawing correlations based on coincidence of data assuming one is the underlying cause of another. Finding causative correlation is a notorious failure in scientific understanding.

In science, correlation studies are often used to test for the existence of interesting patterns, but they are never used exclusively to claim a cause. In order to make a causal claim you must run an experiment or series of experiments and further studies using the scientific method — i.e., test to see if it really is a cause by altering parameters and performing more experiments, making predictions and testing them. We validate that one event is indeed directly influencing the other and is the reason behind the detected correlation.


US spending on science, space, and technology and Suicides by hanging, strangulation and suffocation
US spending on science, space, and technology and Suicides by hanging, strangulation and suffocation

The term “risk factor” is used in medicine to mean “something that is positively correlated.” For instance, obesity is a risk factor for Type 2 diabetes. The term is often incorrectly understood to mean “cause” (e.g. “I’m at risk for diabetes? But I’m not fat!”). Alternatively, a clear risk factor can be disputed on the basis that it’s not a definitive cause — a classic use of the uncertainty tactic (e.g. “I smoke three packs a day and I don’t have cancer!”).


Healthcare, and the rest of the world, is driving future results with measurement and predictive correlation based on huge data sets. This has proven to be effective and often times an accurate prediction of outcome. It is, by far, the system that, outside of learning algorithms, is used to determine a predictive event. To say it clearly, past data that correlates is used as a deterministic prediction of future results. So obesity is predictive of diabetes, cigarette smoking is predictive of lung cancer, anxiety is predictive of heart disease, diabetes, and asthma. It is however, not predictive in the certainty range required for true decision making. That would be in the range of 94% to 99%.
What has been discussed so far is single factor correlation and, as most know, banks and insurance companies use multi-factored correlation to determine your risk profile for loans and insurance rates. Of course it is worth stealing advanced methods from insurance and actuarial methods to determine the risk and predictions for health care. They are, in fact, one in the same thing. Aligning real-time methods using multi factored correlation from sensor data for health will go a long way towards mitigating the future cost of health care for an elderly population explosion in coincidence with a burgeoning population of obesity.

Financial Modeling, Actuarial Valuation and Solvency in Insurance
by Mario V. Wüthrich, Michael Merz
The point of this discussion is that the technology of off the shelf IoT systems with analytics are not going to provide the the solutions medical institutions are hoping will mitigate the burden of elderly health care through preventative maintenance and multi-factored correlation. This problem, of determining the characteristics of the data and the solution that best applies to the application area is exactly what Zanthion is addressing. We are addressing these issues by iterating through the needs of the system; secure multi subscriber transport of data, device data collection for the non-technical, filtering and correcting data so that it is clean and appropriate, analytics that determine predictability and expected percentage of correctness, and easily implemented integration with third party applications used for reward based on behavior.
The goal is to remediate before disaster and provide substantive assisted living, nursing home, and city and county community intervention that lowers the risk of catastrophic disaster. Companies will accomplish this by crowd sourcing opt in remediation from neighbors and using the share economy to provide just in time services like companionship or transport. The result of this methodology is the predictive capability of a need for intervention by neighbors, by family, or by emergency services. With future systems like the one currently offered by Zanthion loved ones, community shared economies, and emergency services will know in real time when:

  • there is more dust because cleaning has decreased dramatically
  • windows are left open on cold nights and thermostats are overworked because the inhabitants have forgotten
  • there is an increase in ammonia because there have been more urinary accidents without follow up washing and drying
  • their mother has fallen out of bed and not gotten back in
  • their father may have fallen in the shower
  • their sister’s pace is slowing over time and they might need a physical therapist
  • a person on oxygen during a flood needs evacuation out of their home
  • a resident in a community has fallen and needs help up by their neighbors

Zanthion is a pioneer in changing our social environment with future vision and use case (solution based) systems that improve the world based on open source, transparent, crowdsourced economic mechanisms that accurately assess what happened, inform the correct resources that the event has occurred, provide resources to the problem efficiently, and keep track of the efficiency of fixing the non-conformity. We embrace a responsible future.